Hieu Pham

Xiangning Chen, Chen Liang, Da Huang et al. · cmu, deepmind

We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program space. To bridge the large generalization gap between proxy and target tasks, we also introduce program selection and simplification strategies. Our method discovers a simple and effective optimization algorithm, $\textbf{Lion}$ ($\textit{Evo$\textbf{L}$ved S$\textbf{i}$gn M$\textbf{o}$me$\textbf{n}$tum}$). It is more memory-efficient than Adam as it only keeps track of the momentum. Different from adaptive optimizers, its update has the same magnitude for each parameter calculated through the sign operation. We compare Lion with widely used optimizers, such as Adam and Adafactor, for training a variety of models on different tasks. On image classification, Lion boosts the accuracy of ViT by up to 2% on ImageNet and saves up to 5x the pre-training compute on JFT. On vision-language contrastive learning, we achieve 88.3% $\textit{zero-shot}$ and 91.1% $\textit{fine-tuning}$ accuracy on ImageNet, surpassing the previous best results by 2% and 0.1%, respectively. On diffusion models, Lion outperforms Adam by achieving a better FID score and reducing the training compute by up to 2.3x. For autoregressive, masked language modeling, and fine-tuning, Lion exhibits a similar or better performance compared to Adam. Our analysis of Lion reveals that its performance gain grows with the training batch size. It also requires a smaller learning rate than Adam due to the larger norm of the update produced by the sign function. Additionally, we examine the limitations of Lion and identify scenarios where its improvements are small or not statistically significant. Lion is also successfully deployed in production systems such as Google search ads CTR model.

Yingtian Zou, Vikas Verma, Sarthak Mittal et al. · cmu, deepmind

Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization performance in many learning paradigms and applications. In this work, we first analyze Mixup and show that it implicitly regularizes infinitely many directional derivatives of all orders. Based on this new insight, we propose an improved version of Mixup, theoretically justified to deliver better generalization performance than the vanilla Mixup. To demonstrate the effectiveness of the proposed method, we conduct experiments across various domains such as images, tabular data, speech, and graphs. Our results show that the proposed method improves Mixup across multiple datasets using a variety of architectures, for instance, exhibiting an improvement over Mixup by 0.8% in ImageNet top-1 accuracy.

Nguyen Tuan, Phi Nguyen, Dai Tran et al.

Early detection and localization of myocardial infarction (MI) can reduce the severity of cardiac damage through timely treatment interventions. In recent years, deep learning techniques have shown promise for detecting MI in echocardiographic images. However, there has been no examination of how segmentation accuracy affects MI classification performance and the potential benefits of using ensemble learning approaches. Our study investigates this relationship and introduces a robust method that combines features from multiple segmentation models to improve MI classification performance by leveraging ensemble learning. Our method combines myocardial segment displacement features from multiple segmentation models, which are then input into a typical classifier to estimate the risk of MI. We validated the proposed approach on two datasets: the public HMC-QU dataset (109 echocardiograms) for training and validation, and an E-Hospital dataset (60 echocardiograms) from a local clinical site in Vietnam for independent testing. Model performance was evaluated based on accuracy, sensitivity, and specificity. The proposed approach demonstrated excellent performance in detecting MI. The results showed that the proposed approach outperformed the state-of-the-art feature-based method. Further research is necessary to determine its potential use in clinical settings as a tool to assist cardiologists and technicians with objective assessments and reduce dependence on operator subjectivity. Our research codes are available on GitHub at https://github.com/vinuni-vishc/mi-detection-echo.

Tue M. Cao, Nhat H. Tran, Phi Le Nguyen et al.

This work discusses the use of contrastive learning and deep learning for diagnosing cardiovascular diseases from electrocardiography (ECG) signals. While the ECG signals usually contain 12 leads (channels), many healthcare facilities and devices lack access to all these 12 leads. This raises the problem of how to use only fewer ECG leads to produce meaningful diagnoses with high performance. We introduce a simple experiment to test whether contrastive learning can be applied to this task. More specifically, we added the similarity between the embedding vectors when the 12 leads signal and the fewer leads ECG signal to the loss function to bring these representations closer together. Despite its simplicity, this has been shown to have improved the performance of diagnosing with all lead combinations, proving the potential of contrastive learning on this task.

Tong Zhou, Chen Ding, Changhong Jing et al.

The relationship between brain structure and function is critical for revealing the pathogenesis of brain disorders, including Alzheimer's disease (AD). However, mapping brain structure to function connections is a very challenging task. In this work, a bidirectional graph generative adversarial network (BG-GAN) is proposed to represent brain structure-function connections. Specifically, by designing a module incorporating inner graph convolution network (InnerGCN), the generators of BG-GAN can employ features of direct and indirect brain regions to learn the mapping function between the structural domain and the functional domain. Besides, a new module named Balancer is designed to counterpoise the optimization between generators and discriminators. By introducing the Balancer into BG-GAN, both the structural generator and functional generator can not only alleviate the issue of mode collapse but also learn complementarity of structural and functional features. Experimental results using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that both generated structure and function connections can improve the identification accuracy of AD. The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence. They also suggest that brain structure is the basis of brain function, and the strong structural connections are majorly accompanied by strong functional connections.

Hieu Pham, Zihang Dai, Qizhe Xie et al.

We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student. Our code will be available at https://github.com/google-research/google-research/tree/master/meta_pseudo_labels.

Hong Nguyen, Hoang Nguyen, Melinda Chang et al.

Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel representation learning method for severity assessment in medical images using Contrastive learningintegrated Preference Optimization. Different from conventional contrastive learning methods that maximize the distance between classes, ConPrO injects into the latent vector the distance preference knowledge between various severity classes and the normal class. We systematically examine the key components of our framework to illuminate how contrastive prediction tasks acquire valuable representations. We show that our representation learning framework offers valuable severity ordering in the feature space while outperforming previous state-of-the-art methods on classification tasks. We achieve a 6% and 20% relative improvement compared to a supervised and a self-supervised baseline, respectively. In addition, we derived discussions on severity indicators and related applications of preference comparison in the medical domain.

Xuhang Chen, Zhuo Li, Yanyan Shen et al.

Functional ultrasound (fUS) imaging provides exceptional spatiotemporal resolution for neurovascular mapping, yet its practical application is significantly hampered by critical challenges. Foremost among these are data scarcity, arising from ethical considerations and signal degradation through the cranium, which collectively limit dataset diversity and compromise the fairness of downstream machine learning models.

Dung T. Tran, Hung Vu, Anh Tran et al.

This paper introduces SEMISE, a novel method for representation learning in medical imaging that combines self-supervised and supervised learning. By leveraging both labeled and augmented data, SEMISE addresses the challenge of data scarcity and enhances the encoder's ability to extract meaningful features. This integrated approach leads to more informative representations, improving performance on downstream tasks. As result, our approach achieved a 12% improvement in classification and a 3% improvement in segmentation, outperforming existing methods. These results demonstrate the potential of SIMESE to advance medical image analysis and offer more accurate solutions for healthcare applications, particularly in contexts where labeled data is limited.

Phu X. Nguyen, Huy Phan, Hieu Pham et al.

Transformer-based foundation models for Electrocardiograms (ECGs) have recently achieved impressive performance in many downstream applications.

Yifei Tang, Hongjie Jiang, Changhong Jing et al.

Functional brain network analysis has become an indispensable tool for brain disease analysis. It is profoundly impacted by deep learning methods, which can characterize complex connections between ROIs. However, the research on foundation models of brain network is limited and constrained to a single dimension, which restricts their extensive application in neuroscience. In this study, we propose a fine-tuned brain network model for brain disease diagnosis. It expands brain region representations across multiple dimensions based on the original brain network model, thereby enhancing its generalizability. Our model consists of two key modules: (1)an adapter module that expands brain region features across different dimensions. (2)a fine-tuned foundation brain network model, based on self-supervised learning and pre-trained on fMRI data from thousands of participants. Specifically, its transformer block is able to effectively extract brain region features and compute the inter-region associations. Moreover, we derive a compact latent representation of the brain network for brain disease diagnosis. Our downstream experiments in this study demonstrate that the proposed model achieves superior performance in brain disease diagnosis, which potentially offers a promising approach in brain network analysis research.

Hiep Dinh, Son Le, My Than et al.

Gait and movement analysis have become a well-established clinical tool for diagnosing health conditions, monitoring disease progression for a wide spectrum of diseases, and to implement and assess treatment, surgery and or rehabilitation interventions. However, quantitative motion assessment remains limited to costly motion capture systems and specialized personnel, restricting its accessibility and broader application. Recent advancements in deep neural networks have enabled quantitative movement analysis using single-camera videos, offering an accessible alternative to conventional motion capture systems. In this paper, we present an efficient approach for clinical gait analysis through a dual-pattern input convolutional Transformer network. The proposed system leverages a dual-input Transformer model to estimate essential gait parameters from single RGB videos captured by a single-view camera. The system demonstrates high accuracy in estimating critical metrics such as the gait deviation index (GDI), knee flexion angle, step length, and walking cadence, validated on a dataset of individuals with movement disorders. Notably, our approach surpasses state-of-the-art methods in various scenarios, using fewer resources and proving highly suitable for clinical application, particularly in resource-constrained environments.

Huyen Le, Khiet Dang, Nhung Nguyen et al.

Human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) are a powerful tool in advancing cardiovascular research and clinical applications. The maturation of sarcomere organization in hiPSC-CMs is crucial, as it supports the contractile function and structural integrity of these cells. Traditional methods for assessing this maturation like manual annotation and feature extraction are labor-intensive, time-consuming, and unsuitable for high-throughput analysis. To address this, we propose D-SarcNet, a dual-stream deep learning framework that takes fluorescent hiPSC-CM single-cell images as input and outputs the stage of the sarcomere structural organization on a scale from 1.0 to 5.0. The framework also integrates Fast Fourier Transform (FFT), deep learning-generated local patterns, and gradient magnitude to capture detailed structural information at both global and local levels. Experiments on a publicly available dataset from the Allen Institute for Cell Science show that the proposed approach not only achieves a Spearman correlation of 0.868 marking a 3.7% improvement over the previous state-of-the-art but also significantly enhances other key performance metrics, including MSE, MAE, and R2 score. Beyond establishing a new state-of-the-art in sarcomere structure assessment from hiPSC-CM images, our ablation studies highlight the significance of integrating global and local information to enhance deep learning networks ability to discern and learn vital visual features of sarcomere structure.

Bowen Hu, Weiheng Yao, Sibo Qiao et al.

In minimally-invasive brain surgeries with indirect and narrow operating environments, 3D brain reconstruction is crucial. However, as requirements of accuracy for some new minimally-invasive surgeries (such as brain-computer interface surgery) are higher and higher, the outputs of conventional 3D reconstruction, such as point cloud (PC), are facing the challenges that sample points are too sparse and the precision is insufficient. On the other hand, there is a scarcity of high-density point cloud datasets, which makes it challenging to train models for direct reconstruction of high-density brain point clouds. In this work, a novel model named stereoscopic-aware graph generative adversarial network (SG-GAN) with two stages is proposed to generate fine high-density PC conditioned on a single image. The Stage-I GAN sketches the primitive shape and basic structure of the organ based on the given image, yielding Stage-I point clouds. The Stage-II GAN takes the results from Stage-I and generates high-density point clouds with detailed features. The Stage-II GAN is capable of correcting defects and restoring the detailed features of the region of interest (ROI) through the up-sampling process. Furthermore, a parameter-free-attention-based free-transforming module is developed to learn the efficient features of input, while upholding a promising performance. Comparing with the existing methods, the SG-GAN model shows superior performance in terms of visual quality, objective measurements, and performance in classification, as demonstrated by comprehensive results measured by several evaluation metrics including PC-to-PC error and Chamfer distance.

Sang Michael Xie, Hieu Pham, Xuanyi Dong et al.

The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affect language model (LM) performance. In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a small proxy model using group distributionally robust optimization (Group DRO) over domains to produce domain weights (mixture proportions) without knowledge of downstream tasks. We then resample a dataset with these domain weights and train a larger, full-sized model. In our experiments, we use DoReMi on a 280M-parameter proxy model to set the domain weights for training an 8B-parameter model (30x larger) more efficiently. On The Pile, DoReMi improves perplexity across all domains, even when it downweights a domain. DoReMi improves average few-shot downstream accuracy by 6.5% points over a baseline model trained using The Pile's default domain weights and reaches the baseline accuracy with 2.6x fewer training steps. On the GLaM dataset, DoReMi, which has no knowledge of downstream tasks, even matches the performance of using domain weights tuned on downstream tasks.

Hieu Pham, Zihang Dai, Golnaz Ghiasi et al.

We present a combined scaling method - named BASIC - that achieves 85.7% top-1 accuracy on the ImageNet ILSVRC-2012 validation set without learning from any labeled ImageNet example. This accuracy surpasses best published similar models - CLIP and ALIGN - by 9.3%. Our BASIC model also shows significant improvements in robustness benchmarks. For instance, on 5 test sets with natural distribution shifts such as ImageNet-{A,R,V2,Sketch} and ObjectNet, our model achieves 84.3% top-1 average accuracy, only a small drop from its original ImageNet accuracy. To achieve these results, we scale up the contrastive learning framework of CLIP and ALIGN in three dimensions: data size, model size, and batch size. Our dataset has 6.6B noisy image-text pairs, which is 4x larger than ALIGN, and 16x larger than CLIP. Our largest model has 3B weights, which is 3.75x larger in parameters and 8x larger in FLOPs than ALIGN and CLIP. Finally, our batch size is 65536 which is 2x more than CLIP and 4x more than ALIGN. We encountered two main challenges with the scaling rules of BASIC. First, the main challenge with implementing the combined scaling rules of BASIC is the limited memory of accelerators, such as GPUs and TPUs. To overcome the memory limit, we propose two simple methods which make use of gradient checkpointing and model parallelism. Second, while increasing the dataset size and the model size has been the defacto method to improve the performance of deep learning models like BASIC, the effect of a large contrastive batch size on such contrastive-trained image-text models is not well-understood. To shed light on the benefits of large contrastive batch sizes, we develop a theoretical framework which shows that larger contrastive batch sizes lead to smaller generalization gaps for image-text models such as BASIC.

Saba Moeinizade, Hieu Pham, Ye Han et al.

For a global breeding organization, identifying the next generation of superior crops is vital for its success. Recognizing new genetic varieties requires years of in-field testing to gather data about the crop's yield, pest resistance, heat resistance, etc. At the conclusion of the growing season, organizations need to determine which varieties will be advanced to the next growing season (or sold to farmers) and which ones will be discarded from the candidate pool. Specifically for soybeans, identifying their relative maturity is a vital piece of information used for advancement decisions. However, this trait needs to be physically observed, and there are resource limitations (time, money, etc.) that bottleneck the data collection process. To combat this, breeding organizations are moving toward advanced image capturing devices. In this paper, we develop a robust and automatic approach for estimating the relative maturity of soybeans using a time series of UAV images. An end-to-end hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) is proposed to extract features and capture the sequential behavior of time series data. The proposed deep learning model was tested on six different environments across the United States. Results suggest the effectiveness of our proposed CNN-LSTM model compared to the local regression method. Furthermore, we demonstrate how this newfound information can be used to aid in plant breeding advancement decisions.

Saeed Khaki, Nima Safaei, Hieu Pham et al.

For a globally recognized planting breeding organization, manually-recorded field observation data is crucial for plant breeding decision making. However, certain phenotypic traits such as plant color, height, kernel counts, etc. can only be collected during a specific time-window of a crop's growth cycle. Due to labor-intensive requirements, only a small subset of possible field observations are recorded each season. To help mitigate this data collection bottleneck in wheat breeding, we propose a novel deep learning framework to accurately and efficiently count wheat heads to aid in the gathering of real-time data for decision making. We call our model WheatNet and show that our approach is robust and accurate for a wide range of environmental conditions of the wheat field. WheatNet uses a truncated MobileNetV2 as a lightweight backbone feature extractor which merges feature maps with different scales to counter image scale variations. Then, extracted multi-scale features go to two parallel sub-networks for simultaneous density-based counting and localization tasks. Our proposed method achieves an MAE and RMSE of 3.85 and 5.19 in our wheat head counting task, respectively, while having significantly fewer parameters when compared to other state-of-the-art methods. Our experiments and comparisons with other state-of-the-art methods demonstrate the superiority and effectiveness of our proposed method.

Hieu Pham, Xinyi Wang, Yiming Yang et al.

Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data. However, several recent works have found that better translation quality of the pseudo-parallel data does not necessarily lead to better final translation models, while lower-quality but more diverse data often yields stronger results. In this paper, we propose a novel method to generate pseudo-parallel data from a pre-trained back-translation model. Our method is a meta-learning algorithm which adapts a pre-trained back-translation model so that the pseudo-parallel data it generates would train a forward-translation model to do well on a validation set. In our evaluations in both the standard datasets WMT En-De'14 and WMT En-Fr'14, as well as a multilingual translation setting, our method leads to significant improvements over strong baselines. Our code will be made available.

Chao Jia, Yinfei Yang, Ye Xia et al.

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) process. This costly curation process limits the size of datasets and hence hinders the scaling of trained models. In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme. Our visual representation achieves strong performance when transferred to classification tasks such as ImageNet and VTAB. The aligned visual and language representations enables zero-shot image classification and also set new state-of-the-art results on Flickr30K and MSCOCO image-text retrieval benchmarks, even when compared with more sophisticated cross-attention models. The representations also enable cross-modality search with complex text and text + image queries.

Hieu Pham, Quoc V. Le

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states. As a result, these conventional methods are less effective than methods that leverage the structures, such as SpatialDropout and DropBlock, which randomly drop the values at certain contiguous areas in the hidden states and setting them to zero. Although the locations of dropout areas random, the patterns of SpatialDropout and DropBlock are manually designed and fixed. Here we propose to learn the dropout patterns. In our method, a controller learns to generate a dropout pattern at every channel and layer of a target network, such as a ConvNet or a Transformer. The target network is then trained with the dropout pattern, and its resulting validation performance is used as a signal for the controller to learn from. We show that this method works well for both image recognition on CIFAR-10 and ImageNet, as well as language modeling on Penn Treebank and WikiText-2. The learned dropout patterns also transfers to different tasks and datasets, such as from language model on Penn Treebank to Engligh-French translation on WMT 2014. Our code will be available.

Saeed Khaki, Hieu Pham, Lizhi Wang

Large-scale crop yield estimation is, in part, made possible due to the availability of remote sensing data allowing for the continuous monitoring of crops throughout their growth cycle. Having this information allows stakeholders the ability to make real-time decisions to maximize yield potential. Although various models exist that predict yield from remote sensing data, there currently does not exist an approach that can estimate yield for multiple crops simultaneously, and thus leads to more accurate predictions. A model that predicts the yield of multiple crops and concurrently considers the interaction between multiple crop yields. We propose a new convolutional neural network model called YieldNet which utilizes a novel deep learning framework that uses transfer learning between corn and soybean yield predictions by sharing the weights of the backbone feature extractor. Additionally, to consider the multi-target response variable, we propose a new loss function. We conduct our experiment using data from 1,132 counties for corn and 1,076 counties for soybean across the United States. Numerical results demonstrate that our proposed method accurately predicts corn and soybean yield from one to four months before the harvest with a MAE being 8.74% and 8.70% of the average yield, respectively, and is competitive to other state-of-the-art approaches.

Vikas Verma, Minh-Thang Luong, Kenji Kawaguchi et al.

Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To overcome such limitation, we propose a novel domain-agnostic approach to contrastive learning, named DACL, that is applicable to domains where invariances, and thus, data augmentation techniques, are not readily available. Key to our approach is the use of Mixup noise to create similar and dissimilar examples by mixing data samples differently either at the input or hidden-state levels. To demonstrate the effectiveness of DACL, we conduct experiments across various domains such as tabular data, images, and graphs. Our results show that DACL not only outperforms other domain-agnostic noising methods, such as Gaussian-noise, but also combines well with domain-specific methods, such as SimCLR, to improve self-supervised visual representation learning. Finally, we theoretically analyze our method and show advantages over the Gaussian-noise based contrastive learning approach.

Arissa Wongpanich, Hieu Pham, James Demmel et al.

EfficientNets are a family of state-of-the-art image classification models based on efficiently scaled convolutional neural networks. Currently, EfficientNets can take on the order of days to train; for example, training an EfficientNet-B0 model takes 23 hours on a Cloud TPU v2-8 node. In this paper, we explore techniques to scale up the training of EfficientNets on TPU-v3 Pods with 2048 cores, motivated by speedups that can be achieved when training at such scales. We discuss optimizations required to scale training to a batch size of 65536 on 1024 TPU-v3 cores, such as selecting large batch optimizers and learning rate schedules as well as utilizing distributed evaluation and batch normalization techniques. Additionally, we present timing and performance benchmarks for EfficientNet models trained on the ImageNet dataset in order to analyze the behavior of EfficientNets at scale. With our optimizations, we are able to train EfficientNet on ImageNet to an accuracy of 83% in 1 hour and 4 minutes.

Saeed Khaki, Hieu Pham, Ye Han et al.

The future landscape of modern farming and plant breeding is rapidly changing due to the complex needs of our society. The explosion of collectable data has started a revolution in agriculture to the point where innovation must occur. To a commercial organization, the accurate and efficient collection of information is necessary to ensure that optimal decisions are made at key points of the breeding cycle. However, due to the shear size of a breeding program and current resource limitations, the ability to collect precise data on individual plants is not possible. In particular, efficient phenotyping of crops to record its color, shape, chemical properties, disease susceptibility, etc. is severely limited due to labor requirements and, oftentimes, expert domain knowledge. In this paper, we propose a deep learning based approach, named DeepStand, for image-based corn stand counting at early phenological stages. The proposed method adopts a truncated VGG-16 network as a backbone feature extractor and merges multiple feature maps with different scales to make the network robust against scale variation. Our extensive computational experiments suggest that our proposed method can successfully count corn stands and out-perform other state-of-the-art methods. It is the goal of our work to be used by the larger agricultural community as a way to enable high-throughput phenotyping without the use of extensive time and labor requirements.

Lawrence Mosley, Hieu Pham, Yogesh Bansal et al.

Modern trends in digital agriculture have seen a shift towards artificial intelligence for crop quality assessment and yield estimation. In this work, we document how a parameter tuned single-shot object detection algorithm can be used to identify and count sorghum head from aerial drone images. Our approach involves a novel exploratory analysis that identified key structural elements of the sorghum images and motivated the selection of parameter-tuned anchor boxes that contributed significantly to performance. These insights led to the development of a deep learning model that outperformed the baseline model and achieved an out-of-sample mean average precision of 0.95.

Saeed Khaki, Hieu Pham, Ye Han et al.

The success of modern farming and plant breeding relies on accurate and efficient collection of data. For a commercial organization that manages large amounts of crops, collecting accurate and consistent data is a bottleneck. Due to limited time and labor, accurately phenotyping crops to record color, head count, height, weight, etc. is severely limited. However, this information, combined with other genetic and environmental factors, is vital for developing new superior crop species that help feed the world's growing population. Recent advances in machine learning, in particular deep learning, have shown promise in mitigating this bottleneck. In this paper, we propose a novel deep learning method for counting on-ear corn kernels in-field to aid in the gathering of real-time data and, ultimately, to improve decision making to maximize yield. We name this approach DeepCorn, and show that this framework is robust under various conditions. DeepCorn estimates the density of corn kernels in an image of corn ears and predicts the number of kernels based on the estimated density map. DeepCorn uses a truncated VGG-16 as a backbone for feature extraction and merges feature maps from multiple scales of the network to make it robust against image scale variations. We also adopt a semi-supervised learning approach to further improve the performance of our proposed method. Our proposed method achieves the MAE and RMSE of 41.36 and 60.27 in the corn kernel counting task, respectively. Our experimental results demonstrate the superiority and effectiveness of our proposed method compared to other state-of-the-art methods.

Saeed Khaki, Hieu Pham, Ye Han et al.

Precise in-season corn grain yield estimates enable farmers to make real-time accurate harvest and grain marketing decisions minimizing possible losses of profitability. A well developed corn ear can have up to 800 kernels, but manually counting the kernels on an ear of corn is labor-intensive, time consuming and prone to human error. From an algorithmic perspective, the detection of the kernels from a single corn ear image is challenging due to the large number of kernels at different angles and very small distance among the kernels. In this paper, we propose a kernel detection and counting method based on a sliding window approach. The proposed method detect and counts all corn kernels in a single corn ear image taken in uncontrolled lighting conditions. The sliding window approach uses a convolutional neural network (CNN) for kernel detection. Then, a non-maximum suppression (NMS) is applied to remove overlapping detections. Finally, windows that are classified as kernel are passed to another CNN regression model for finding the (x,y) coordinates of the center of kernel image patches. Our experiments indicate that the proposed method can successfully detect the corn kernels with a low detection error and is also able to detect kernels on a batch of corn ears positioned at different angles.

Xinyi Wang, Hieu Pham, Paul Michel et al.

To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems. Similarly, a machine learning model could potentially be trained better with a scorer that "adapts" to its current learning state and estimates the importance of each training data instance. Training such an adaptive scorer efficiently is a challenging problem; in order to precisely quantify the effect of a data instance at a given time during the training, it is typically necessary to first complete the entire training process. To efficiently optimize data usage, we propose a reinforcement learning approach called Differentiable Data Selection (DDS). In DDS, we formulate a scorer network as a learnable function of the training data, which can be efficiently updated along with the main model being trained. Specifically, DDS updates the scorer with an intuitive reward signal: it should up-weigh the data that has a similar gradient with a dev set upon which we would finally like to perform well. Without significant computing overhead, DDS delivers strong and consistent improvements over several strong baselines on two very different tasks of machine translation and image classification.

Mohsen Shahhosseini, Guiping Hu, Hieu Pham

Aggregating multiple learners through an ensemble of models aim to make better predictions by capturing the underlying distribution of the data more accurately. Different ensembling methods, such as bagging, boosting, and stacking/blending, have been studied and adopted extensively in research and practice. While bagging and boosting focus more on reducing variance and bias, respectively, stacking approaches target both by finding the optimal way to combine base learners. In stacking with the weighted average, ensembles are created from weighted averages of multiple base learners. It is known that tuning hyperparameters of each base learner inside the ensemble weight optimization process can produce better performing ensembles. To this end, an optimization-based nested algorithm that considers tuning hyperparameters as well as finding the optimal weights to combine ensembles (Generalized Weighted Ensemble with Internally Tuned Hyperparameters (GEM-ITH)) is designed. Besides, Bayesian search was used to speed-up the optimizing process, and a heuristic was implemented to generate diverse and well-performing base learners. The algorithm is shown to be generalizable to real data sets through analyses with ten publicly available data sets.

Xinyi Wang, Hieu Pham, Philip Arthur et al.

Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the face of paucity of data. In this paper, we propose Soft Decoupled Encoding (SDE), a multilingual lexicon encoding framework specifically designed to share lexical-level information intelligently without requiring heuristic preprocessing such as pre-segmenting the data. SDE represents a word by its spelling through a character encoding, and its semantic meaning through a latent embedding space shared by all languages. Experiments on a standard dataset of four low-resource languages show consistent improvements over strong multilingual NMT baselines, with gains of up to 2 BLEU on one of the tested languages, achieving the new state-of-the-art on all four language pairs.

Xinyi Wang, Hieu Pham, Pengcheng Yin et al.

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU.

Xinyi Wang, Hieu Pham, Zihang Dai et al.

In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three translation datasets of different scales show that SwitchOut yields consistent improvements of about 0.5 BLEU, achieving better or comparable performances to strong alternatives such as word dropout (Sennrich et al., 2016a). Code to implement this method is included in the appendix.

Hieu Pham, Melody Y. Guan, Barret Zoph et al.

We propose Efficient Neural Architecture Search (ENAS), a fast and inexpensive approach for automatic model design. In ENAS, a controller learns to discover neural network architectures by searching for an optimal subgraph within a large computational graph. The controller is trained with policy gradient to select a subgraph that maximizes the expected reward on the validation set. Meanwhile the model corresponding to the selected subgraph is trained to minimize a canonical cross entropy loss. Thanks to parameter sharing between child models, ENAS is fast: it delivers strong empirical performances using much fewer GPU-hours than all existing automatic model design approaches, and notably, 1000x less expensive than standard Neural Architecture Search. On the Penn Treebank dataset, ENAS discovers a novel architecture that achieves a test perplexity of 55.8, establishing a new state-of-the-art among all methods without post-training processing. On the CIFAR-10 dataset, ENAS designs novel architectures that achieve a test error of 2.89%, which is on par with NASNet (Zoph et al., 2018), whose test error is 2.65%.

Azalia Mirhoseini, Hieu Pham, Quoc V. Le et al.

The past few years have witnessed a growth in size and computational requirements for training and inference with neural networks. Currently, a common approach to address these requirements is to use a heterogeneous distributed environment with a mixture of hardware devices such as CPUs and GPUs. Importantly, the decision of placing parts of the neural models on devices is often made by human experts based on simple heuristics and intuitions. In this paper, we propose a method which learns to optimize device placement for TensorFlow computational graphs. Key to our method is the use of a sequence-to-sequence model to predict which subsets of operations in a TensorFlow graph should run on which of the available devices. The execution time of the predicted placements is then used as the reward signal to optimize the parameters of the sequence-to-sequence model. Our main result is that on Inception-V3 for ImageNet classification, and on RNN LSTM, for language modeling and neural machine translation, our model finds non-trivial device placements that outperform hand-crafted heuristics and traditional algorithmic methods.

Irwan Bello, Hieu Pham, Quoc V. Le et al.

This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city coordinates, predicts a distribution over different city permutations. Using negative tour length as the reward signal, we optimize the parameters of the recurrent network using a policy gradient method. We compare learning the network parameters on a set of training graphs against learning them on individual test graphs. Despite the computational expense, without much engineering and heuristic designing, Neural Combinatorial Optimization achieves close to optimal results on 2D Euclidean graphs with up to 100 nodes. Applied to the KnapSack, another NP-hard problem, the same method obtains optimal solutions for instances with up to 200 items.

Minh-Thang Luong, Hieu Pham, Christopher D. Manning

An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has been little work exploring useful architectures for attention-based NMT. This paper examines two simple and effective classes of attentional mechanism: a global approach which always attends to all source words and a local one that only looks at a subset of source words at a time. We demonstrate the effectiveness of both approaches over the WMT translation tasks between English and German in both directions. With local attention, we achieve a significant gain of 5.0 BLEU points over non-attentional systems which already incorporate known techniques such as dropout. Our ensemble model using different attention architectures has established a new state-of-the-art result in the WMT'15 English to German translation task with 25.9 BLEU points, an improvement of 1.0 BLEU points over the existing best system backed by NMT and an n-gram reranker.